Softmax gradient policy for variance minimization and risk-averse multi armed bandits
cs.LG, cs.AI, cs.NA, math.NA
Submitted: 2026-03-31
Updated: 2026-09-23
Code: https://github.com/gabriel-turinici/min_variance_and_risk_averse_softmax_MAB
Terminology
Sources
- On the Convergence of SGD with Biased Gradients
- Variance-Optimal Arm Selection: Misallocation Minimization and Best Arm Identification
- Impact of QCD sum rules coupling constants on neutron stars structure
- End to End Learning for Self-Driving Cars
- Distributional Reinforcement Learning with Quantile Regression
- On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems
- GPT-4 Technical Report
- Generalized Risk-Aversion in Stochastic Multi-Armed Bandits
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks